Structured survey of human factor-related maritime accident research

Shi, Xin; Zhuang, Huizhao; Xu, Dong

doi:10.1016/j.oceaneng.2021.109561

Cited by 37 publications

(9 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Human factors, such as working conditions and individual factors, have also been considered as risk factors for maritime accidents [5], [6], [17]- [19]. Zhang et al explore various combinations of human factors that have been shown to affect outbreaks of maritime accidents [20].…”

Section: A Maritime Risk Assessment and Accident Preventionmentioning

confidence: 99%

“…In other words, these types of maritime accidents are predictable and thus preventable to some degree. In fact, a number of existing works on maritime accident risk assessment use quantitative logs for developing accident prediction models [6]- [8]. This work proposes a maritime accident prediction system that uses accident logs, most of which are deemed to be predictable to some extent, and various risk factors associated with these accidents.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development of an Interpretable Maritime Accident Prediction System Using Machine Learning Techniques

Kim

Lim

2022

IEEE Access

View full text Add to dashboard Cite

Every year, maritime accidents cause severe damages not only to humans but also to maritime instruments like vessels. The authors of this work therefore propose a machine learning-based maritime accident prediction system that can be used to prevent maritime accidents from happening by predicting and interpreting the accidents. This work overcomes the limitations of the existing works that lack practicability in the sense that the ex-post analyses are conducted to suggest accident prevention strategies but maritime accidents are not analyzed holistically. Using extensive literature reviews and expert interviews, a large number of risk factors associated with maritime accidents are identified, and related data are collected and utilized in the work. Throughout variable selection, data retrieval, hot-spot identification, and the maritime accident prediction model construction process, various machine learning algorithms are exploited in order to construct an organized system. In addition, interpretations for the resulting accident predictions are given using interpretable machine learning algorithms so as to provide explainable results to users. Finally, the proposed system is evaluated using a SERVQUAL model and proves its effectiveness in real-world applications.INDEX TERMS Maritime accident, ocean engineering, accident prediction, interpretable machine learning.

show abstract

Section: A Maritime Risk Assessment and Accident Preventionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Development of an Interpretable Maritime Accident Prediction System Using Machine Learning Techniques

Kim

Lim

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Research on maritime management is extensive, and most of them conceptualize it as an event or a cause/consequence [10][11][12][13]. This line of research focuses on maritime accidents [14], Port State Control (PSC) inspections [4,15], and the marine environment [16]. This static vision of traditional maritime management is essential because it lays the core foundation for future research.…”

Section: Of 17mentioning

confidence: 99%

The Coevolutionary Process of Maritime Management of Shipping Industry in the Context of the COVID-19 Pandemic

Zhang

2021

JMSE

View full text Add to dashboard Cite

This study investigates how international organizations, International Maritime Organization (IMO) member states, and associate members have embarked on maritime management (MM) measures to address dire situations in the context of the COVID-19 pandemic. It explores the evolution of MM practices from international organizations, IMO member states, and associate members to ensure the resilience and sustainability of the shipping industry. Corpus linguistics was employed as a computer-assisted method to assess a large number of naturally occurring texts. Circular letters from international organizations and member states listed on the IMO website from January 2020 to July 2021 were curated and built into three corpora. Through corpus linguistic analysis of circulars from three different crisis phases (Pre-/early-crisis, Crisis in progress, Post-COVID-19 crisis phase), we discovered an MM progression mechanism developed between stakeholders in conjunction with the post-crisis period. The study presented the “MM-as-process” vision to emphasize the time-varying dynamic nature of MM development during the disruption.

show abstract

“…In practical applications, a quantitative method based on the analytic hierarchy process has been mainly used to analyse the failure indicators of ship personnel risk mitigation status [ 3 , 4 ]. This method has been successfully applied to human accident analysis, crew capability building, and crew comprehensive quality evaluation [ 5 , 6 ]. Additionally, in recent years, with the continuous development of science and technology, risk mitigation auxiliary technologies such as video surveillance, risk perception, and information communication in ship risk mitigation have also been widely applied [ 7 , 8 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

A Model to Evaluate the Effectiveness of the Maritime Shipping Risk Mitigation System by Entropy-Based Capability Degradation Analysis

Jun

Qiao

2022

IJERPH

View full text Add to dashboard Cite

Accurate evaluation of the risk mitigation status of navigating ships is essential for guaranteeing navigational safety. This research mainly focuses on the feasibility and accuracy of evaluating the real effectiveness of a risk mitigation system for navigating ships, including addressing the problem of immeasurableness for risk mitigation capability and determining the degradation regulation of risk mitigation capability over time. The proposed method to solve the problem is an effectiveness evaluation model based on the capability perspective, composed of a capability measurement algorithm based on entropy theory and capability degradation regulation analysis based on numerical process fitting. First, combined with the theoretical framework of a comprehensive defence system, the risk mitigation system designed for navigating ships is reconstructed based on capability building. Second, using a numerical fitting method, the degradation regulation of risk mitigation capability with time is obtained to improve the accuracy of the dynamic evaluation. Finally, referring to entropy theory, the uncertainty of capability is calculated, and then the model is constructed based on this uncertainty to realize the effectiveness evaluation from a capability perspective. The results obtained in an application test of the proposed model indicate that using the entropy of capability can realize an accurate effectiveness evaluation of a risk mitigation system for navigating ships, with a 9% improvement in accuracy, and the Weibull curve fitting is more consistent with capability degradation regulation, with a signification level of 2.5%. The proposed model provides a new path for evaluating the effectiveness of a risk mitigation system for navigating ships from the entropy of capability, and compared with the traditional probabilistic method, the model is more realistic and accurate in actual applications.

show abstract

Structured survey of human factor-related maritime accident research

Cited by 37 publications

References 61 publications

Development of an Interpretable Maritime Accident Prediction System Using Machine Learning Techniques

Development of an Interpretable Maritime Accident Prediction System Using Machine Learning Techniques

The Coevolutionary Process of Maritime Management of Shipping Industry in the Context of the COVID-19 Pandemic

A Model to Evaluate the Effectiveness of the Maritime Shipping Risk Mitigation System by Entropy-Based Capability Degradation Analysis

Contact Info

Product

Resources

About